Truncation

Crossing out the oldest turns

Library › Context Problems

1. The Context Window

2. Window Occupancy

3. Growth per Turn

4. Remaining Space

5. Turn Budget

6. Retrieval Footprint

7. Retrieval per Turn

8. Search Rounds

9. Window Sizing

10. Truncation

11. Compaction

12. The Compaction Bill

13. Compacted Retrieval

14. The Compaction Threshold

15. Verbatim Tail

16. Stateless API

17. Retrieval Cost

18. Context Tax

19. Quadratic Cost

20. Cost Forecast

Truncation is the crudest fix for a full window: cross out the earliest turns until the new message has room. It is cheap and it always works, which is why agents do it, and it costs the beginning of the conversation, which is usually the part that said what the conversation was for. Turns go whole. You cannot drop half a turn, so the count always rounds up and a little more is thrown away than strictly had to be.

---

⬇ Truncation worksheet (2 pages)

---

Next:
11. Compaction